Proceedings of the AAAI Conference on Artificial Intelligence · 2022 · 94 citations · 72 references
ComputingComputer ScienceCybersecurityComputer SecurityComputer VisionMachine LearningAdversary TacticsAdversary TechniquesAdversarial Attack DetectionAdversarial ExamplesAdversarial SearchQuery EvaluationSparse ModelsSuccess Rate Analysis
We propose a versatile framework based on random search, Sparse-RS, for score-based sparse targeted and untargeted attacks in the black-box setting. Sparse-RS does not rely on substitute models and achieves state-of-the-art success rate and query efficiency for multiple sparse attack models: L0-bounded perturbations, adversarial patches, and adversarial frames. The L0-version of untargeted Sparse-RS outperforms all black-box and even all white-box attacks for different models on MNIST, CIFAR-10, and ImageNet. Moreover, our untargeted Sparse-RS achieves very high success rates even for the challenging settings of 20x20 adversarial patches and 2-pixel wide adversarial frames for 224x224 images. Finally, we show that Sparse-RS can be applied to generate targeted universal adversarial patches where it significantly outperforms the existing approaches. Our code is available at https://github.com/fra31/sparse-rs.
72
The Unreasonable Effectiveness of Deep Features as a Perceptual Metric
Richard Zhang, Phillip Isola, Alexei A. Efros et al. · 2018 · 12.4K citations
Intriguing properties of neural networks
Christian Szegedy, Wojciech Zaremba, Ilya Sutskever et al. · arXiv (Cornell University) · 2013 · 5.7K citations · Full text
The Limitations of Deep Learning in Adversarial Settings
Nicolas Papernot, Patrick McDaniel, Somesh Jha et al. · 2016 · 3.9K citations